Susceptibility of AutoML mortality prediction algorithms to model drift caused by the COVID pandemic.
Simone Maria KagerbauerBernhard UlmArmin Horst PodtschaskeDimislav Ivanov AndonovManfred BlobnerBettina JungwirthMartin GraessnerPublished in: BMC Medical Informatics Decis. Mak. (2024)
Keyphrases
- theoretical analysis
- linear models
- prediction model
- computational model
- probabilistic model
- prediction algorithm
- hidden markov models
- computational complexity
- maximum likelihood
- mathematical model
- statistical model
- neural network model
- formal model
- high level
- learning models
- learning algorithm
- computational cost
- worst case
- cost function
- statistical methods
- hybrid model
- decision trees